Triple

T2802368
Position Surface form Disambiguated ID Type / Status
Subject Battle of Puebla E53175 entity
Predicate FrenchCommander P19844 FINISHED
Object Charles de Lorencez
Charles de Lorencez was a French general best known for leading the ill-fated French assault against Mexican forces at the Battle of Puebla in 1862.
E444941 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Charles de Lorencez | Statement: [Battle of Puebla, FrenchCommander, Charles de Lorencez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles de Lorencez
Context triple: [Battle of Puebla, FrenchCommander, Charles de Lorencez]
  • A. Henri Contet
    Henri Contet was a French lyricist known for writing songs for prominent chanson artists in the mid-20th century.
  • B. Léon Boyer
    Léon Boyer was a French civil engineer best known for designing major 19th-century railway structures, including the Garabit Viaduct.
  • C. François Dupeyron
    François Dupeyron was a French film director and screenwriter known for his humanistic, character-driven dramas.
  • D. Henri Lebasque
    Henri Lebasque was a French post-impressionist painter known for his luminous use of color and intimate domestic and landscape scenes.
  • E. Louis Jeantet
    Louis Jeantet was a Swiss businessman and philanthropist whose foundation established one of Europe’s most prestigious awards in biomedical research.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Charles de Lorencez
Triple: [Battle of Puebla, FrenchCommander, Charles de Lorencez]
Generated description
Charles de Lorencez was a French general best known for leading the ill-fated French assault against Mexican forces at the Battle of Puebla in 1862.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Charles de Lorencez
Target entity description: Charles de Lorencez was a French general best known for leading the ill-fated French assault against Mexican forces at the Battle of Puebla in 1862.
  • A. Henri Contet
    Henri Contet was a French lyricist known for writing songs for prominent chanson artists in the mid-20th century.
  • B. Léon Boyer
    Léon Boyer was a French civil engineer best known for designing major 19th-century railway structures, including the Garabit Viaduct.
  • C. François Dupeyron
    François Dupeyron was a French film director and screenwriter known for his humanistic, character-driven dramas.
  • D. Henri Lebasque
    Henri Lebasque was a French post-impressionist painter known for his luminous use of color and intimate domestic and landscape scenes.
  • E. Louis Jeantet
    Louis Jeantet was a Swiss businessman and philanthropist whose foundation established one of Europe’s most prestigious awards in biomedical research.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ab495a90788190941b6917e1eca3a6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abde12b33481908b276760a922db9c completed March 7, 2026, 8:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6720e877481908d870653bbb09820 completed March 15, 2026, 8:47 a.m.
NEDg Description generation batch_69b6727e314c819096e6aa6cda67d6f7 completed March 15, 2026, 8:49 a.m.
NED2 Entity disambiguation (via description) batch_69b672c3816c8190806144d98d51a484 completed March 15, 2026, 8:50 a.m.
Created at: March 6, 2026, 9:58 p.m.